Xiaowei Huang

Full Professor, University of Liverpool

Joined

July 2019

Names

Xiaowei Huang

Emails

****@liverpool.ac.uk (Confirmed)

Personal Links

Career & Education History

Full Professor

University of Liverpool (liverpool.ac.uk)

Present

Advisors, Relations & Conflicts

Coauthor

Present

Expertise

AI Safety

2018 – Present

Trustworthy AI

2015 – Present

Verification and Validation

2008 – Present

Publications

BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation
Zheng Zhou, Wenquan Feng, Shuchang Lyu, Guangliang Cheng, Xiaowei Huang, Qi Zhao
- Submitted to ICLR 2026
- Readers: Everyone
ThermoRL: Structure-Aware RL for Protein Mutation Design to Enhance Thermostability
Xiangwen Wang, Ronghui Mu, Gaojie Jin, Xiaowei Huang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
S²R²: Semantic Segment Robustness Regularisation on Prompt Perturbation
Zhuoyun Li, Boxuan Wang, Zhenglin Huang, Qisong He, Xinmiao Huang, Guangliang Cheng, Xiaowei Huang, Yi Dong
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
So-Fake: Benchmarking Social Media Image Forgery Detection
Zhenglin Huang, Tianxiao Li, Xiangtai Li, Haiquan Wen, Yiwei He, Jiangning Zhang, Hao Fei, Xi Yang, Baoyuan Wu, Xiaowei Huang, Bei Peng, Guangliang Cheng
- Submitted to ICLR 2026
- Readers: Everyone
F1-Reasoner: Synthesizing Verifiable Reasoning Data From Formal Math Statements
Zihao Zhou, Wei Liu, Xinlong Fu, Kaizhu Huang, Xiaowei Huang, Meng Fang, Wenda Li, Qiufeng Wang
- Submitted to ICLR 2026
- Readers: Everyone
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang
- ICLR 2026 Poster
- Readers: Everyone
AI for Science Strategic Compass: Aligning Discovery Tensions with Core AI Functions
Ran Liu, Zhibin Lin, Xiaowei Huang
- NeurIPS2025-AI4Science Poster
- Readers: Everyone
Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model
Sihao Wu, Gaojie Jin, Wei Huang, Jianhong Wang, Xiaowei Huang
- ACML 2025 Conference Track
- Readers: Everyone
Evaluating Human–LLM Alignment Requires Transparent and Adaptable Statistical Guarantees
Gaojie Jin, Yicheng Lin, Shuaitong Liu, Yan Du, Tianjin Huang, Lijie Hu, Di Wang, Xiaowei Huang
- Submitted to NeurIPS 2025 Position Paper Track
- Readers: Everyone
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang
- NeurIPS 2025 poster
- Readers: Everyone

View all 73 publications

Co-Authors

View all 185 co-authors